001//////////////////////////////////////////////////////////////////////////////// 002// checkstyle: Checks Java source code for adherence to a set of rules. 003// Copyright (C) 2001-2020 the original author or authors. 004// 005// This library is free software; you can redistribute it and/or 006// modify it under the terms of the GNU Lesser General Public 007// License as published by the Free Software Foundation; either 008// version 2.1 of the License, or (at your option) any later version. 009// 010// This library is distributed in the hope that it will be useful, 011// but WITHOUT ANY WARRANTY; without even the implied warranty of 012// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 013// Lesser General Public License for more details. 014// 015// You should have received a copy of the GNU Lesser General Public 016// License along with this library; if not, write to the Free Software 017// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA 018//////////////////////////////////////////////////////////////////////////////// 019 020package com.puppycrawl.tools.checkstyle.checks.coding; 021 022import java.util.ArrayList; 023import java.util.BitSet; 024import java.util.HashMap; 025import java.util.List; 026import java.util.Map; 027import java.util.regex.Pattern; 028 029import com.puppycrawl.tools.checkstyle.FileStatefulCheck; 030import com.puppycrawl.tools.checkstyle.api.AbstractCheck; 031import com.puppycrawl.tools.checkstyle.api.DetailAST; 032import com.puppycrawl.tools.checkstyle.api.TokenTypes; 033import com.puppycrawl.tools.checkstyle.utils.TokenUtil; 034 035/** 036 * <p> 037 * Checks for multiple occurrences of the same string literal within a single file. 038 * </p> 039 * <p> 040 * Rationale: Code duplication makes maintenance more difficult, so it can be better 041 * to replace the multiple occurrences with a constant. 042 * </p> 043 * <ul> 044 * <li> 045 * Property {@code allowedDuplicates} - Specify the maximum number of occurrences 046 * to allow without generating a warning. 047 * Default value is {@code 1}. 048 * </li> 049 * <li> 050 * Property {@code ignoreStringsRegexp} - Specify RegExp for ignored strings (with quotation marks). 051 * Default value is {@code "^""$"}. 052 * </li> 053 * <li> 054 * Property {@code ignoreOccurrenceContext} - Specify token type names where duplicate 055 * strings are ignored even if they don't match ignoredStringsRegexp. This allows you to 056 * exclude syntactical contexts like annotations or static initializers from the check. 057 * Default value is {@code ANNOTATION}. 058 * </li> 059 * </ul> 060 * <p> 061 * To configure the check: 062 * </p> 063 * <pre> 064 * <module name="MultipleStringLiterals"/> 065 * </pre> 066 * <p> 067 * To configure the check so that it allows two occurrences of each string: 068 * </p> 069 * <pre> 070 * <module name="MultipleStringLiterals"> 071 * <property name="allowedDuplicates" value="2"/> 072 * </module> 073 * </pre> 074 * <p> 075 * To configure the check so that it ignores ", " and empty strings: 076 * </p> 077 * <pre> 078 * <module name="MultipleStringLiterals"> 079 * <property name="ignoreStringsRegexp" 080 * value='^(("")|(", "))$'/> 081 * </module> 082 * </pre> 083 * <p> 084 * To configure the check so that it flags duplicate strings in all syntactical contexts, 085 * even in annotations like {@code @SuppressWarnings("unchecked")}: 086 * </p> 087 * <pre> 088 * <module name="MultipleStringLiterals"> 089 * <property name="ignoreOccurrenceContext" value=""/> 090 * </module> 091 * </pre> 092 * 093 * @since 3.5 094 */ 095@FileStatefulCheck 096public class MultipleStringLiteralsCheck extends AbstractCheck { 097 098 /** 099 * A key is pointing to the warning message text in "messages.properties" 100 * file. 101 */ 102 public static final String MSG_KEY = "multiple.string.literal"; 103 104 /** 105 * The found strings and their tokens. 106 */ 107 private final Map<String, List<DetailAST>> stringMap = new HashMap<>(); 108 109 /** 110 * Specify token type names where duplicate strings are ignored even if they 111 * don't match ignoredStringsRegexp. This allows you to exclude syntactical 112 * contexts like annotations or static initializers from the check. 113 */ 114 private final BitSet ignoreOccurrenceContext = new BitSet(); 115 116 /** 117 * Specify the maximum number of occurrences to allow without generating a warning. 118 */ 119 private int allowedDuplicates = 1; 120 121 /** 122 * Specify RegExp for ignored strings (with quotation marks). 123 */ 124 private Pattern ignoreStringsRegexp; 125 126 /** 127 * Construct an instance with default values. 128 */ 129 public MultipleStringLiteralsCheck() { 130 setIgnoreStringsRegexp(Pattern.compile("^\"\"$")); 131 ignoreOccurrenceContext.set(TokenTypes.ANNOTATION); 132 } 133 134 /** 135 * Setter to specify the maximum number of occurrences to allow without generating a warning. 136 * @param allowedDuplicates The maximum number of duplicates. 137 */ 138 public void setAllowedDuplicates(int allowedDuplicates) { 139 this.allowedDuplicates = allowedDuplicates; 140 } 141 142 /** 143 * Setter to specify RegExp for ignored strings (with quotation marks). 144 * @param ignoreStringsRegexp 145 * regular expression pattern for ignored strings 146 * @noinspection WeakerAccess 147 */ 148 public final void setIgnoreStringsRegexp(Pattern ignoreStringsRegexp) { 149 if (ignoreStringsRegexp == null || ignoreStringsRegexp.pattern().isEmpty()) { 150 this.ignoreStringsRegexp = null; 151 } 152 else { 153 this.ignoreStringsRegexp = ignoreStringsRegexp; 154 } 155 } 156 157 /** 158 * Setter to specify token type names where duplicate strings are ignored even 159 * if they don't match ignoredStringsRegexp. This allows you to exclude 160 * syntactical contexts like annotations or static initializers from the check. 161 * @param strRep the string representation of the tokens interested in 162 */ 163 public final void setIgnoreOccurrenceContext(String... strRep) { 164 ignoreOccurrenceContext.clear(); 165 for (final String s : strRep) { 166 final int type = TokenUtil.getTokenId(s); 167 ignoreOccurrenceContext.set(type); 168 } 169 } 170 171 @Override 172 public int[] getDefaultTokens() { 173 return getRequiredTokens(); 174 } 175 176 @Override 177 public int[] getAcceptableTokens() { 178 return getRequiredTokens(); 179 } 180 181 @Override 182 public int[] getRequiredTokens() { 183 return new int[] {TokenTypes.STRING_LITERAL}; 184 } 185 186 @Override 187 public void visitToken(DetailAST ast) { 188 if (!isInIgnoreOccurrenceContext(ast)) { 189 final String currentString = ast.getText(); 190 if (ignoreStringsRegexp == null || !ignoreStringsRegexp.matcher(currentString).find()) { 191 stringMap.computeIfAbsent(currentString, key -> new ArrayList<>()).add(ast); 192 } 193 } 194 } 195 196 /** 197 * Analyses the path from the AST root to a given AST for occurrences 198 * of the token types in {@link #ignoreOccurrenceContext}. 199 * 200 * @param ast the node from where to start searching towards the root node 201 * @return whether the path from the root node to ast contains one of the 202 * token type in {@link #ignoreOccurrenceContext}. 203 */ 204 private boolean isInIgnoreOccurrenceContext(DetailAST ast) { 205 boolean isInIgnoreOccurrenceContext = false; 206 for (DetailAST token = ast; 207 token.getParent() != null; 208 token = token.getParent()) { 209 final int type = token.getType(); 210 if (ignoreOccurrenceContext.get(type)) { 211 isInIgnoreOccurrenceContext = true; 212 break; 213 } 214 } 215 return isInIgnoreOccurrenceContext; 216 } 217 218 @Override 219 public void beginTree(DetailAST rootAST) { 220 stringMap.clear(); 221 } 222 223 @Override 224 public void finishTree(DetailAST rootAST) { 225 for (Map.Entry<String, List<DetailAST>> stringListEntry : stringMap.entrySet()) { 226 final List<DetailAST> hits = stringListEntry.getValue(); 227 if (hits.size() > allowedDuplicates) { 228 final DetailAST firstFinding = hits.get(0); 229 log(firstFinding, MSG_KEY, stringListEntry.getKey(), hits.size()); 230 } 231 } 232 } 233 234}